glorv
glorv
> There's something about this that surprises me. Namely, should tracing really incur a 15% overhead if the tracing level is low? That seems shocking. @glorv any interest in providing...
I have 2 questions about this PR: 1. Is it possible to directly retry applying the snapshot if the failure is caused by unexpected(maybe some IO layer) error? 2. Why...
> Introduce a new RPC to instruct the leader to resend the snapshot, which may change lots of code. Why need this extra RPC? At the leader side, it will...
> Do you mean persisting the previous state so it can be restored even after restarting TiKV? Yes. But I think just update the peer's state to its previous status...
> Correct me if I'm wrong, but I think that removing the peer and making PD add one fresh peer sounds valid ? As the peer, which panics due to...
@LykxSassinator from https://github.com/tikv/tikv/blob/06eed732641ad47aec44dd58aa3d64e18c1c5ee8/components/raftstore/src/store/fsm/store.rs#L2114-L2130 It seems after tombstoning the peer, the region will drop all following raft messages, thus the peer won't be recovered automatically.
/cc @overvenus @Connor1996 @SpadeA-Tang @LykxSassinator @v01dstar PTAL